Noninvasive Diabetes Detection through Human Breath Using TinyML-Powered E-Nose
Volatile organic compounds (VOCs) in exhaled human breath serve as pivotal biomarkers for disease identification and medical diagnostics. In the context of diabetes mellitus, the noninvasive detection of acetone, a primary biomarker using electronic noses (e-noses), has gained significant attention....
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/4/1294 |
| _version_ | 1797296995198566400 |
|---|---|
| author | Alberto Gudiño-Ochoa Julio Alberto García-Rodríguez Raquel Ochoa-Ornelas Jorge Ivan Cuevas-Chávez Daniel Alejandro Sánchez-Arias |
| author_facet | Alberto Gudiño-Ochoa Julio Alberto García-Rodríguez Raquel Ochoa-Ornelas Jorge Ivan Cuevas-Chávez Daniel Alejandro Sánchez-Arias |
| author_sort | Alberto Gudiño-Ochoa |
| collection | DOAJ |
| description | Volatile organic compounds (VOCs) in exhaled human breath serve as pivotal biomarkers for disease identification and medical diagnostics. In the context of diabetes mellitus, the noninvasive detection of acetone, a primary biomarker using electronic noses (e-noses), has gained significant attention. However, employing e-noses requires pre-trained algorithms for precise diabetes detection, often requiring a computer with a programming environment to classify newly acquired data. This study focuses on the development of an embedded system integrating Tiny Machine Learning (TinyML) and an e-nose equipped with Metal Oxide Semiconductor (MOS) sensors for real-time diabetes detection. The study encompassed 44 individuals, comprising 22 healthy individuals and 22 diagnosed with various types of diabetes mellitus. Test results highlight the XGBoost Machine Learning algorithm’s achievement of 95% detection accuracy. Additionally, the integration of deep learning algorithms, particularly deep neural networks (DNNs) and one-dimensional convolutional neural network (1D-CNN), yielded a detection efficacy of 94.44%. These outcomes underscore the potency of combining e-noses with TinyML in embedded systems, offering a noninvasive approach for diabetes mellitus detection. |
| first_indexed | 2024-03-07T22:13:51Z |
| format | Article |
| id | doaj.art-4169115f9ad44994af3b895830588654 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-07T22:13:51Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4169115f9ad44994af3b8958305886542024-02-23T15:34:05ZengMDPI AGSensors1424-82202024-02-01244129410.3390/s24041294Noninvasive Diabetes Detection through Human Breath Using TinyML-Powered E-NoseAlberto Gudiño-Ochoa0Julio Alberto García-Rodríguez1Raquel Ochoa-Ornelas2Jorge Ivan Cuevas-Chávez3Daniel Alejandro Sánchez-Arias4Electronics Department, Tecnológico Nacional de México/Instituto Tecnológico de Ciudad Guzmán, Ciudad Guzmán 49100, MexicoCentro Universitario del Sur, Departamento de Ciencias Computacionales e Innovación Tecnológica, Universidad de Guadalajara, Ciudad Guzmán 49000, MexicoSystems and Computation Department, Tecnológico Nacional de México/Instituto Tecnológico de Ciudad Guzmán, Ciudad Guzmán 49100, MexicoElectronics Department, Tecnológico Nacional de México/Instituto Tecnológico de Ciudad Guzmán, Ciudad Guzmán 49100, MexicoElectronics Department, Tecnológico Nacional de México/Instituto Tecnológico de Ciudad Guzmán, Ciudad Guzmán 49100, MexicoVolatile organic compounds (VOCs) in exhaled human breath serve as pivotal biomarkers for disease identification and medical diagnostics. In the context of diabetes mellitus, the noninvasive detection of acetone, a primary biomarker using electronic noses (e-noses), has gained significant attention. However, employing e-noses requires pre-trained algorithms for precise diabetes detection, often requiring a computer with a programming environment to classify newly acquired data. This study focuses on the development of an embedded system integrating Tiny Machine Learning (TinyML) and an e-nose equipped with Metal Oxide Semiconductor (MOS) sensors for real-time diabetes detection. The study encompassed 44 individuals, comprising 22 healthy individuals and 22 diagnosed with various types of diabetes mellitus. Test results highlight the XGBoost Machine Learning algorithm’s achievement of 95% detection accuracy. Additionally, the integration of deep learning algorithms, particularly deep neural networks (DNNs) and one-dimensional convolutional neural network (1D-CNN), yielded a detection efficacy of 94.44%. These outcomes underscore the potency of combining e-noses with TinyML in embedded systems, offering a noninvasive approach for diabetes mellitus detection.https://www.mdpi.com/1424-8220/24/4/1294electronic nosediabetes mellitusTinyMLexhaled-breath analysisVOCsTensorFlowLite |
| spellingShingle | Alberto Gudiño-Ochoa Julio Alberto García-Rodríguez Raquel Ochoa-Ornelas Jorge Ivan Cuevas-Chávez Daniel Alejandro Sánchez-Arias Noninvasive Diabetes Detection through Human Breath Using TinyML-Powered E-Nose Sensors electronic nose diabetes mellitus TinyML exhaled-breath analysis VOCs TensorFlowLite |
| title | Noninvasive Diabetes Detection through Human Breath Using TinyML-Powered E-Nose |
| title_full | Noninvasive Diabetes Detection through Human Breath Using TinyML-Powered E-Nose |
| title_fullStr | Noninvasive Diabetes Detection through Human Breath Using TinyML-Powered E-Nose |
| title_full_unstemmed | Noninvasive Diabetes Detection through Human Breath Using TinyML-Powered E-Nose |
| title_short | Noninvasive Diabetes Detection through Human Breath Using TinyML-Powered E-Nose |
| title_sort | noninvasive diabetes detection through human breath using tinyml powered e nose |
| topic | electronic nose diabetes mellitus TinyML exhaled-breath analysis VOCs TensorFlowLite |
| url | https://www.mdpi.com/1424-8220/24/4/1294 |
| work_keys_str_mv | AT albertogudinoochoa noninvasivediabetesdetectionthroughhumanbreathusingtinymlpoweredenose AT julioalbertogarciarodriguez noninvasivediabetesdetectionthroughhumanbreathusingtinymlpoweredenose AT raquelochoaornelas noninvasivediabetesdetectionthroughhumanbreathusingtinymlpoweredenose AT jorgeivancuevaschavez noninvasivediabetesdetectionthroughhumanbreathusingtinymlpoweredenose AT danielalejandrosanchezarias noninvasivediabetesdetectionthroughhumanbreathusingtinymlpoweredenose |